Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385992052> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4385992052 endingPage "181" @default.
- W4385992052 startingPage "165" @default.
- W4385992052 abstract "Oracle character recognition has recently made significant progress with the success of deep neural networks (DNNs), but it is far from being solved. Most works do not consider the long-tailed distribution issue in oracle character recognition, resulting in a biased DNN towards head classes. To overcome this issue, we propose a two-stage decoupled learning method to train an unbiased DNN model for long-tailed oracle character recognition. In the first stage, we optimize the DNN under instance-balanced sampling, obtaining a robust backbone but biased classifier. In the second stage, we propose two strategies to refine the classifier under class-balanced sampling. Specifically, we add a learnable weight scaling module which can adjust the classifier to respect tail classes; meanwhile, we integrate the KL-divergence loss to maintain attention to head classes through knowledge distillation from the first stage. Coupling these two designs enables us to train an unbiased DNN model in oracle character recognition. Our proposed method achieves new state-of-the-art performance on three benchmark datasets, including OBC306, Oracle-AYNU and Oracle-20K." @default.
- W4385992052 created "2023-08-19" @default.
- W4385992052 creator A5012677271 @default.
- W4385992052 creator A5026022035 @default.
- W4385992052 creator A5053452551 @default.
- W4385992052 creator A5065037360 @default.
- W4385992052 creator A5073528771 @default.
- W4385992052 creator A5078813046 @default.
- W4385992052 date "2023-01-01" @default.
- W4385992052 modified "2023-10-14" @default.
- W4385992052 title "Decoupled Learning for Long-Tailed Oracle Character Recognition" @default.
- W4385992052 cites W2023639956 @default.
- W4385992052 cites W2148143831 @default.
- W4385992052 cites W2185824196 @default.
- W4385992052 cites W2963691377 @default.
- W4385992052 cites W2992308087 @default.
- W4385992052 cites W3003466563 @default.
- W4385992052 cites W3004249119 @default.
- W4385992052 cites W3034368386 @default.
- W4385992052 cites W3096121526 @default.
- W4385992052 cites W3171998492 @default.
- W4385992052 cites W3174366534 @default.
- W4385992052 cites W3176474016 @default.
- W4385992052 cites W3196600796 @default.
- W4385992052 cites W4247050319 @default.
- W4385992052 cites W4312877479 @default.
- W4385992052 cites W4313156423 @default.
- W4385992052 doi "https://doi.org/10.1007/978-3-031-41685-9_11" @default.
- W4385992052 hasPublicationYear "2023" @default.
- W4385992052 type Work @default.
- W4385992052 citedByCount "0" @default.
- W4385992052 crossrefType "book-chapter" @default.
- W4385992052 hasAuthorship W4385992052A5012677271 @default.
- W4385992052 hasAuthorship W4385992052A5026022035 @default.
- W4385992052 hasAuthorship W4385992052A5053452551 @default.
- W4385992052 hasAuthorship W4385992052A5065037360 @default.
- W4385992052 hasAuthorship W4385992052A5073528771 @default.
- W4385992052 hasAuthorship W4385992052A5078813046 @default.
- W4385992052 hasConcept C115903868 @default.
- W4385992052 hasConcept C119857082 @default.
- W4385992052 hasConcept C153180895 @default.
- W4385992052 hasConcept C154945302 @default.
- W4385992052 hasConcept C2984842247 @default.
- W4385992052 hasConcept C41008148 @default.
- W4385992052 hasConcept C50644808 @default.
- W4385992052 hasConcept C55166926 @default.
- W4385992052 hasConcept C95623464 @default.
- W4385992052 hasConceptScore W4385992052C115903868 @default.
- W4385992052 hasConceptScore W4385992052C119857082 @default.
- W4385992052 hasConceptScore W4385992052C153180895 @default.
- W4385992052 hasConceptScore W4385992052C154945302 @default.
- W4385992052 hasConceptScore W4385992052C2984842247 @default.
- W4385992052 hasConceptScore W4385992052C41008148 @default.
- W4385992052 hasConceptScore W4385992052C50644808 @default.
- W4385992052 hasConceptScore W4385992052C55166926 @default.
- W4385992052 hasConceptScore W4385992052C95623464 @default.
- W4385992052 hasLocation W43859920521 @default.
- W4385992052 hasOpenAccess W4385992052 @default.
- W4385992052 hasPrimaryLocation W43859920521 @default.
- W4385992052 hasRelatedWork W2045932760 @default.
- W4385992052 hasRelatedWork W2073713056 @default.
- W4385992052 hasRelatedWork W2110441383 @default.
- W4385992052 hasRelatedWork W2125620709 @default.
- W4385992052 hasRelatedWork W2184228419 @default.
- W4385992052 hasRelatedWork W2326878701 @default.
- W4385992052 hasRelatedWork W2734997742 @default.
- W4385992052 hasRelatedWork W3110702597 @default.
- W4385992052 hasRelatedWork W4293864700 @default.
- W4385992052 hasRelatedWork W67445448 @default.
- W4385992052 isParatext "false" @default.
- W4385992052 isRetracted "false" @default.
- W4385992052 workType "book-chapter" @default.